[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71RR7GMR3Y9G7JTAD87B4PV":3,"skill-same:01M71RR7GMR3Y9G7JTAD87B4PV":71},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":55,"updatedAt":56,"install":57,"resources":70},"01M71RR7GMR3Y9G7JTAD87B4PV","agent-cleaner-skills",null,"Identify unused Codex skills and MCP servers and disable them to reduce system-prompt context bloat. Use when the user asks to clean up \u002F slim \u002F 瘦身 their Codex skills or MCP servers, audit which are unused, or recover context budget.","legendtkl\u002Fagent-cleaner","legendtkl","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F2370761?v=4","01M71RR3WRQC40G964Q2GVDMND","01M71RR3XD9TJ7YJEPRSX523JG",3,"MIT","https:\u002F\u002Fgithub.com\u002Flegendtkl\u002Fagent-cleaner\u002Fblob\u002Fmain\u002Fplugins\u002Fcodex\u002Fskills\u002Fagent-cleaner-skills\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"agent cleaner skills","clean","when","unused","servers","codex skills","bloat","reduce","which","slim","MCP","up","use","context budget","prompt","system","Budget","audit","mcp servers","codex","2026-11-10 13:02:02",false,"---\nname: agent-cleaner-skills\ndescription: Identify unused Codex skills and MCP servers and disable them to reduce system-prompt context bloat. Use when the user asks to clean up \u002F slim \u002F 瘦身 their Codex skills or MCP servers, audit which are unused, or recover context budget.\n---\n\n# agent-cleaner — Codex skills and MCP server slimming\n\nWhen the user wants to slim Codex skills or MCP servers, follow the same\nflow: enumerate → suggest → confirm → disable. The CLI exposes parallel\n`skills` and `mcp` command trees on Codex (subagents are Claude Code-only).\n\n## 1. Locate the bundled CLI\n\nPrefer `${AGENT_CLEANER_CLI}` if set. Otherwise locate the newest installed bundle:\n\n```bash\nfind \"${CODEX_HOME:-$HOME\u002F.codex}\u002Fplugins\u002Fcache\u002Flocal\u002Fagent-cleaner\" -path '*\u002Flib\u002Fagent-cleaner.mjs' -type f 2>\u002Fdev\u002Fnull | sort | tail -1\n```\n\nIf that finds nothing, check the current repository path:\n\n```bash\ntest -f plugins\u002Fcodex\u002Flib\u002Fagent-cleaner.mjs && pwd\n```\n\nAlways invoke via `node \u003Cabs-path>` and always pass `--host=codex`.\n\n## 2. Listing and suggesting\n\n```bash\nnode \"\u003Cabs-path>\u002Fagent-cleaner.mjs\" --host=codex skills suggest --json\n```\n\nThe output is a JSON array of suggestions, each with `id`, `name`, `source`, `reason` (`never-used` | `stale`), `confidence` (`high` | `medium` | `low`), `details`.\n\nIf the user wants to see all skills, use `skills list --json`.\n\n## 3. Confirm with the user\n\nShow the suggestion list as a compact table with id, reason, and confidence. Never disable without explicit user confirmation.\n\nIf the user wants to adjust the staleness threshold, mention `--unused-for=60d` (or `2w`, `3m`, `1y`) or persist a default in `~\u002F.agent-cleaner\u002Fconfig.json`:\n\n```json\n{ \"unusedForDays\": 60 }\n```\n\n## 4. Disable\n\nEither pass specific ids:\n\n```bash\nnode \"\u003Cabs-path>\u002Fagent-cleaner.mjs\" --host=codex skills disable user:codex:lark-mail plugin:gmail@openai-curated:gmail --yes\n```\n\nOr apply all current suggestions in one shot:\n\n```bash\nnode \"\u003Cabs-path>\u002Fagent-cleaner.mjs\" --host=codex skills disable --all-suggested --yes\n```\n\nAfter disable succeeds, tell the user: \"Disabled N skills. Restart Codex or start a new Codex session for the change to take effect.\"\n\n## 5. Other operations\n\n- `skills enable \u003Cid...>` — undo a disable.\n- `skills status [--json]` — list currently-disabled skills and detect\u002Fauto-reapply any that an upstream plugin or skill update may have restored.\n- `skills list --json` — full inventory with `lastUsed` and `callCount`.\n\n## 6. MCP servers\n\nThe same verbs apply with `mcp` instead of `skills`. Codex MCP servers live as\n`[mcp_servers.NAME]` blocks in `~\u002F.codex\u002Fconfig.toml`:\n\n```bash\nnode \"\u003Cabs-path>\u002Fagent-cleaner.mjs\" --host=codex mcp suggest --json\nnode \"\u003Cabs-path>\u002Fagent-cleaner.mjs\" --host=codex mcp disable mcp:user:codex:linear --yes\nnode \"\u003Cabs-path>\u002Fagent-cleaner.mjs\" --host=codex mcp disable --all-suggested --yes\n```\n\nUsage is detected from `mcp__\u003Cserver>__\u003Ctool>` tool calls in Codex session\ntranscripts under `~\u002F.codex\u002Fsessions\u002F`.\n\n## Constraints\n\n- Codex system skills under `~\u002F.codex\u002Fskills\u002F.system` cannot be disabled.\n- Skills disable: `mv SKILL.md SKILL.md.agent-cleaner-disabled`. MCP disable:\n  the `[mcp_servers.NAME]` block is spliced out of `config.toml` and the\n  original lines are stashed in state. `enable` reverses both.\n- State is kept at `~\u002F.agent-cleaner\u002Fstate-codex.json`.\n","# agent-cleaner — Codex skills and MCP server slimming\n\nWhen the user wants to slim Codex skills or MCP servers, follow the same\nflow: enumerate → suggest → confirm → disable. The CLI exposes parallel\n`skills` and `mcp` command trees on Codex (subagents are Claude Code-only).\n\n## 1. Locate the bundled CLI\n\nPrefer `${AGENT_CLEANER_CLI}` if set. Otherwise locate the newest installed bundle:\n\n```bash\nfind \"${CODEX_HOME:-$HOME\u002F.codex}\u002Fplugins\u002Fcache\u002Flocal\u002Fagent-cleaner\" -path '*\u002Flib\u002Fagent-cleaner.mjs' -type f 2>\u002Fdev\u002Fnull | sort | tail -1\n```\n\nIf that finds nothing, check the current repository path:\n\n```bash\ntest -f plugins\u002Fcodex\u002Flib\u002Fagent-cleaner.mjs && pwd\n```\n\nAlways invoke via `node \u003Cabs-path>` and always pass `--host=codex`.\n\n## 2. Listing and suggesting\n\n```bash\nnode \"\u003Cabs-path>\u002Fagent-cleaner.mjs\" --host=codex skills suggest --json\n```\n\nThe output is a JSON array of suggestions, each with `id`, `name`, `source`, `reason` (`never-used` | `stale`), `confidence` (`high` | `medium` | `low`), `details`.\n\nIf the user wants to see all skills, use `skills list --json`.\n\n## 3. Confirm with the user\n\nShow the suggestion list as a compact table with id, reason, and confidence. Never disable without explicit user confirmation.\n\nIf the user wants to adjust the staleness threshold, mention `--unused-for=60d` (or `2w`, `3m`, `1y`) or persist a default in `~\u002F.agent-cleaner\u002Fconfig.json`:\n\n```json\n{ \"unusedForDays\": 60 }\n```\n\n## 4. Disable\n\nEither pass specific ids:\n\n```bash\nnode \"\u003Cabs-path>\u002Fagent-cleaner.mjs\" --host=codex skills disable user:codex:lark-mail plugin:gmail@openai-curated:gmail --yes\n```\n\nOr apply all current suggestions in one shot:\n\n```bash\nnode \"\u003Cabs-path>\u002Fagent-cleaner.mjs\" --host=codex skills disable --all-suggested --yes\n```\n\nAfter disable succeeds, tell the user: \"Disabled N skills. Restart Codex or start a new Codex session for the change to take effect.\"\n\n## 5. Other operations\n\n- `skills enable \u003Cid...>` — undo a disable.\n- `skills status [--json]` — list currently-disabled skills and detect\u002Fauto-reapply any that an upstream plugin or skill update may have restored.\n- `skills list --json` — full inventory with `lastUsed` and `callCount`.\n\n## 6. MCP servers\n\nThe same verbs apply with `mcp` instead of `skills`. Codex MCP servers live as\n`[mcp_servers.NAME]` blocks in `~\u002F.codex\u002Fconfig.toml`:\n\n```bash\nnode \"\u003Cabs-path>\u002Fagent-cleaner.mjs\" --host=codex mcp suggest --json\nnode \"\u003Cabs-path>\u002Fagent-cleaner.mjs\" --host=codex mcp disable mcp:user:codex:linear --yes\nnode \"\u003Cabs-path>\u002Fagent-cleaner.mjs\" --host=codex mcp disable --all-suggested --yes\n```\n\nUsage is detected from `mcp__\u003Cserver>__\u003Ctool>` tool calls in Codex session\ntranscripts under `~\u002F.codex\u002Fsessions\u002F`.\n\n## Constraints\n\n- Codex system skills under `~\u002F.codex\u002Fskills\u002F.system` cannot be disabled.\n- Skills disable: `mv SKILL.md SKILL.md.agent-cleaner-disabled`. MCP disable:\n  the `[mcp_servers.NAME]` block is spliced out of `config.toml` and the\n  original lines are stashed in state. `enable` reverses both.\n- State is kept at `~\u002F.agent-cleaner\u002Fstate-codex.json`.\n",{"name":5,"description":7},"main","f7ac29364416fd62f3ec6bf2d4ec34101710a5cf","plugins\u002Fcodex\u002Fskills\u002Fagent-cleaner-skills",0,"https:\u002F\u002Fgithub.com\u002Flegendtkl\u002Fagent-cleaner","https:\u002F\u002Fgithub.com\u002Flegendtkl","http:\u002F\u002Fwww.legendtkl.com","No secret before debugging.\r\n","2026-05-11 11:17:22",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add legendtkl\u002Fagent-cleaner --skill agent-cleaner-skills",{"tool":63,"command":64},"bunx","bunx skills add legendtkl\u002Fagent-cleaner --skill agent-cleaner-skills",{"tool":66,"command":67},"pnpm","pnpm dlx skills add legendtkl\u002Fagent-cleaner --skill agent-cleaner-skills","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flegendtkl\u002Fagent-cleaner\u002Fblob\u002Fmain\u002Fplugins\u002Fcodex\u002Fskills\u002Fagent-cleaner-skills\u002FSKILL.md",true,[],[72,81,91],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":43},"01M71RRATE35P90NDC2P4DN0YZ","foo","A test skill named foo","https:\u002F\u002Fgithub.com\u002Flegendtkl\u002Fagent-cleaner\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Ffoo\u002FSKILL.md",[],[74,79,80],"Test Skill","test",{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":43},"01M71RR9W7N4DFXFVDS6SX92ED","bar","飞书 — bar with quoted Chinese","https:\u002F\u002Fgithub.com\u002Flegendtkl\u002Fagent-cleaner\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fbar\u002FSKILL.md",[],[83,88,89,90],"quoted","with","chinese",{"skillNo":92,"name":5,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":97,"publishedAt":43},"01M71RR5CRA4JH4KCCCV2ZEG8A","Identify unused Claude Code skills, subagents, and MCP servers and disable them to reduce system-prompt context bloat. Use when the user asks to clean up \u002F slim \u002F 瘦身 their installed skills, subagents, or MCP servers, audit which are unused, or recover context budget.","https:\u002F\u002Fgithub.com\u002Flegendtkl\u002Fagent-cleaner\u002Fblob\u002Fmain\u002Fplugins\u002Fclaude-code\u002Fskills\u002Fagent-cleaner-skills\u002FSKILL.md",[96],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[23,31,25,26,27,29,30,33,32,24,34,35,36,37,38,39,40,41,98,99],"code","claude code skills"]